Re: [PATCH 1/2] mm: compaction: consider the number of scanning compound pages in isolate fail path

[Baolin Wang]

On 3/15/2023 11:54 PM, Vlastimil Babka wrote:
> On 3/13/23 11:37, Baolin Wang wrote:
> > The commit b717d6b93b54 ("mm: compaction: include compound page count
> > for scanning in pageblock isolation") had added compound page statistics
> > for scanning in pageblock isolation, to make sure the number of scanned
> > pages are always larger than the number of isolated pages when isolating
> > mirgratable or free pageblock.
> >
> > However, when failed to isolate the pages when scanning the mirgratable or
> > free pageblock, the isolation failure path did not consider the scanning
> > statistics of the compound pages, which can show the incorrect number of
> > scanned pages in tracepoints or the vmstats to make people confusing about
> > the page scanning pressure in memory compaction.
> >
> > Thus we should take into account the number of scanning pages when failed
> > to isolate the compound pages to make the statistics accurate.
> >
> > Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
> > ---
> >   mm/compaction.c | 6 +++---
> >   1 file changed, 3 insertions(+), 3 deletions(-)
> >
> > diff --git a/mm/compaction.c b/mm/compaction.c
> > index 5a9501e0ae01..c9d9ad958e2a 100644
> > --- a/mm/compaction.c
> > +++ b/mm/compaction.c
> > @@ -587,6 +587,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
> >   				blockpfn += (1UL << order) - 1;
> >   				cursor += (1UL << order) - 1;
> >   			}
> > +			nr_scanned += (1UL << order) - 1;
>
> I'd rather put it in the block above that tests order < MAX_ORDER. Otherwise
> as the comments say, the value can be bogus as it's racy.

Right, thanks for pointing it out. Will do in next version.

> >   			goto isolate_fail;
> >   		}
> >   
> > @@ -873,9 +874,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
> >   			cond_resched();
> >   		}
> >   
> > -		nr_scanned++;
> > -
> >   		page = pfn_to_page(low_pfn);
> > +		nr_scanned += compound_nr(page);
>
> For the same reason, I'd rather leave the nr_scanned adjustment by order in
> the specific code blocks where we know/think we have a compound or huge page
> and have sanity checked the order/nr_pages, and not add an unchecked
> compound_nr() here.

OK. Sound reasonable to me. Thanks for your input.

> >   		/*
> >   		 * Check if the pageblock has already been marked skipped.
> > @@ -1077,6 +1077,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
> >   			 */
> >   			if (unlikely(PageCompound(page) && !cc->alloc_contig)) {
> >   				low_pfn += compound_nr(page) - 1;
> > +				nr_scanned += compound_nr(page) - 1;
> >   				SetPageLRU(page);
> >   				goto isolate_fail_put;
> >   			}
> > @@ -1097,7 +1098,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
> >   isolate_success_no_list:
> >   		cc->nr_migratepages += compound_nr(page);
> >   		nr_isolated += compound_nr(page);
> > -		nr_scanned += compound_nr(page) - 1;
> >   
> >   		/*
> >   		 * Avoid isolating too much unless this block is being